Composed Physics- and Data-driven System Identification for Non-autonomous Systems in Control Engineering

被引:3
作者
Goette, Ricarda-Samantha [1 ]
Timmermann, Julia [1 ]
机构
[1] Paderborn Univ, Heinz Nixdorf Inst, Paderborn, Germany
来源
2022 3RD INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, ROBOTICS AND CONTROL, AIRC | 2022年
关键词
data-driven; physics-based; physics-informed; neural networks; system identification; hybrid modelling;
D O I
10.1109/AIRC56195.2022.9836982
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In control design most control strategies are model-based and require accurate models to be applied successfully. Due to simplifications and the model-reality-gap physics-derived models frequently exhibit deviations from real-world-systems. Likewise, purely data-driven methods often do not generalise well enough and may violate physical laws. Recently Physics-Guided Neural Networks (PGNN) and physics-inspired loss functions separately have shown promising results to conquer these drawbacks. In this contribution we extend existing methods towards the identification of non-autonomous systems and propose a combined approach PGNN-L, which uses a PGNN and a physics-inspired loss term (-L) to successfully identify the system's dynamics, while maintaining the consistency with physical laws. The proposed method is demonstrated on two real-world nonlinear systems and outperforms existing techniques regarding complexity and reliability.
引用
收藏
页码:67 / 76
页数:10
相关论文
共 28 条
[1]  
Antonelo EA, 2022, Arxiv, DOI [arXiv:2104.02556, DOI 10.48550/ARXIV.2104.02556]
[2]  
Bishop C., 2006, Pattern Recognition and Machine Learning
[3]   Sparse Identification of Nonlinear Dynamics with Control (SINDYc) [J].
Brunton, Steven L. ;
Proctor, Joshua L. ;
Kutz, J. Nathan .
IFAC PAPERSONLINE, 2016, 49 (18) :710-715
[4]  
Chang YC, 2020, Arxiv, DOI arXiv:2005.00611
[5]   Neural Observer and Adaptive Neural Control Design for a Class of Nonlinear Systems [J].
Chen, Bing ;
Zhang, Huaguang ;
Liu, Xiaoping ;
Lin, Chong .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (09) :4261-4271
[6]  
Chen Ricky T. Q., 2018, Advances in Neural Information Processing Systems, V31
[7]   APPROXIMATION CAPABILITY TO FUNCTIONS OF SEVERAL VARIABLES, NONLINEAR FUNCTIONALS, AND OPERATORS BY RADIAL BASIS FUNCTION NEURAL NETWORKS [J].
CHEN, TP ;
CHEN, H .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1995, 6 (04) :904-910
[8]  
Cranmer M, 2020, Arxiv, DOI arXiv:2003.04630
[9]  
Daw A., 2017, arXiv, DOI DOI 10.48550/ARXIV.1710.11431
[10]  
Daw A, 2019, Arxiv, DOI arXiv:1911.02682